Related work

The foundational work on continual learning, 1991 to 2026: methods, theory, benchmarks, surveys, and the neuroscience of memory. Updated weekly; some carry our notes.

8 papers of 4,574Sort Recent · Most cited
  1. 2025
    Infusing Fine-Grained Visual Knowledge to Vision-Language ModelsNikolaos-Antonios Ypsilantis, Kaifeng Chen, Andre B. Araujo, Ondřej ChumICCV · Czech Technical University in Prague · Google (United States) · +1
    PDF ↗
  2. 2025
    Continual Learning of Large Language Models: A Comprehensive SurveyHaizhou Shi, Zihao Xu, Hengyi Wang … Hao WangACM Computing Surveys · Rutgers, The State University of New Jersey · Google (United States) · +1
    PDF ↗
  3. 2024
    Human-like Learning in Temporally Structured EnvironmentsMatt Jones, Tyler R. Scott, Michael C. MozerAAAI · University of Colorado System · Google (United States) · +1
    PDF ↗
  4. 2022
    Towards Continual Reinforcement Learning: A Review and PerspectivesKhimya Khetarpal, Matthew Riemer, Irina Rish, Doina PrecupJournal of Artificial Intelligence Research · Google DeepMind (United Kingdom) · McGill University · +2
    PDF ↗
  5. 2022
    Sequential changepoint detection in neural networks with checkpointsMichalis K. Titsias, Jakub Sygnowski, Yutian ChenStatistics and Computing · Google DeepMind (United Kingdom)
    PDF ↗
  6. 2021
    Gated Linear NetworksJoel Veness, Tor Lattimore, David Budden … Marcus HütterAAAI · Google DeepMind (United Kingdom)
    PDF ↗
  7. 2021
    Online Limited Memory Neural-Linear Bandits with Likelihood MatchingOfir Nabati, Tom Zahavy, Shie MannorICML · Technion – Israel Institute of Technology · Google DeepMind (United Kingdom)
    PDF ↗
  8. 2017
    Overcoming catastrophic forgetting in neural networksJames Kirkpatrick, Razvan Pascanu, Neil C. Rabinowitz … Raia HadsellPNAS · Google DeepMind (United Kingdom) · Imperial College London
    PDF ↗
About this index

We keep this list because we read the field and wanted one place to see it. It covers work on continual learning itself, in the core areas of machine learning, and leaves out papers that apply it inside another field, such as medical imaging or fault diagnosis. It lists only papers we have a reason to trust: published at a venue like NeurIPS, ICML, ICLR, CVPR or TPAMI, or led by someone who has published there, or cited a few hundred times, and only papers with a PDF we can point you at, so every title opens the paper itself. Preprints that later get accepted, and authors who later publish at those venues, are picked up by the weekly run. It is seeded from the community lists kept by ContinualAI and by Xialei Liu, then filled out from OpenAlex, and every week a script looks for new papers on OpenAlex and arXiv. A model reads each candidate and decides whether it belongs; a person reviews the additions before they go live. Authors and affiliations come from OpenAlex, so a recent preprint can lack its institutions for a week or two.

Missing something, or filed under the wrong venue? Write to hello@unify.ai with the arXiv id or DOI.